Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agents that run while I sleep

claudecodecamp.com

Post reply on HN
Print view View original

361–370 of 532 posts

Re: Agents that run while I sleep

#361

Post by josephg »

mewpmewp2 wrote: post #330
josephg wrote: post #297

Earlier quoted context omitted.

Testing works because tests are (essentially) a second, crappy implementation of your software. Tests only pass if both implementations of your software behave the same way. Usually that will only happen if the test and the code are both correct. Imagine if your code (without tests) has a 5% defect rate. And the tests have a 5% defect rate (with 100% test coverage). Then ideally, you will have a 5%^2 defect rate afte…

I think there is a difference whether you do TDD or write tests after the fact to avoid regression. TDD can only work decently if you already know your specs very well, but not so much when you still need to figure them out, and need to build something actual to be able to figure it out.

Yes; I think this remains true with coding agents. If you need to do some exploration of the solution space, it makes sense to do that before writing tests. Once you have a clear, workable design, you can get the agent to make a battery of tests to make sure the final product works correctly.

Re: Agents that run while I sleep

#362

Post by macgyverismo »

Aachen wrote: post #360

And here I am turning my computer off at night for energy consumption, while others run a few extra ones for... for what, anyway? If you're working on problems real people are having (diseases, climate change, poverty, etc.) then sure, but exacerbating the energy transition for a blog post and your personal brand as OP seems to do? How's that not criminal

It's not criminal as the power usage is (assumed to be) paid for. It is criminal or at least problematic that the cost of power does not include (negative) externalities, we should strive to change that.

Re: Agents that run while I sleep

#363

Post by lazystar »

Aachen wrote: post #360

And here I am turning my computer off at night for energy consumption, while others run a few extra ones for... for what, anyway? If you're working on problems real people are having (diseases, climate change, poverty, etc.) then sure, but exacerbating the energy transition for a blog post and your personal brand as OP seems to do? How's that not criminal

> How's that not criminal

Well, a) it's a hobby, and b) this is still a free country/free society.

Re: Agents that run while I sleep

#364

Post by Tepix »

Just because you can let Claude run overnight doesn't mean it makes sense if you can no longer review what it has done.

If you don't review the result, who is going to want to use or even pay for this slop?

Reviewing is the new bottleneck. If you cannot review any more code, stop producing new code.

Re: Agents that run while I sleep

#365

Post by adamddev1 »

Tests cannot show the absence of bugs.

These are fundamentals of CS that we are forgetting as we dismantle all truth and keep rocketing forward into LLM psychosis.

> I care about this. I don't want to push slop, and I had no real answer.

The answer is to write and understand code. You can't not want to push slop, and also want to just use LLMs.

Re: Agents that run while I sleep

#366

Post by ionwake »

Aachen wrote: post #360

And here I am turning my computer off at night for energy consumption, while others run a few extra ones for... for what, anyway? If you're working on problems real people are having (diseases, climate change, poverty, etc.) then sure, but exacerbating the energy transition for a blog post and your personal brand as OP seems to do? How's that not criminal

I found your post interesting, Im just trying to understand your POV.

If you are on a sinking ship would you not do your best to position yourself?

Or do you see your actions morally equivalent to others regardless of scale?

Re: Agents that run while I sleep

#367

Post by hrmtst93837 »

SoftTalker wrote: post #18
RealityVoid wrote: post #4

It's... really the same problem when you hire people to just write tests. A lot of time it just confirms that the code does what the code does. Having clear specs of what the code should do make things better and clearer.

Yep, tests written after the fact are just verifying tautologies. > Most teams don't [write tests first] because thinking through what the code should do before writing it takes time they don't have. It's astonishing to me how much our industry repeats the same mistakes over and over. This doesn't seem like what other engineering disciplines do. Or is this just me not knowing what it looks like behind the curtain of…

[flagged]

Re: Agents that run while I sleep

#368

Post by wreath »

otabdeveloper4 wrote: post #355
wreath wrote: post #314

Earlier quoted context omitted.

Exactly! How do other parts of the organization deal with this avalanche of features in terms of documenting, pricing and packaging, marketing, selling and getting feedback on them. How do users adopt these features and incorporate them in their workflows so fast? Never in my career was the speed of writing code alone the bottleneck.

> deal with this avalanche of features You mean avalanche of bugs and technical debt.

Technical debt is never a problem now since only AI reads code /s

Re: Agents that run while I sleep

#369

Post by UK-Al05 »

what wrote: post #200
bhouston wrote: post #32

I call this "Test Theatre" and it is real. I wrote about it last year: https://benhouston3d.com/blog/the-rise-of-test-theater You have to actively work against it.

Test theatre isn’t new. Most people writing tests do the exact same thing, testing implementation.

This is why people don't see the problem with tests that agents generate after the implementation. They look exactly like what they write.

Re: Agents that run while I sleep

#370

Post by baq »

otabdeveloper4 wrote: post #349
brobdingnagians wrote: post #300

Earlier quoted context omitted.

I would encourage my competitors to use AI agents on their codebase as much as possible. Make sure every new feature has it, lots of velocity! Run those suckers day and night. Don't review it, just make sure the feature is there! Then when the music stops, the AI companies hit the economic realities, go insolvent, and they are left with no one who understands a sprawling tangled web of code that is 80% AI generated,…

> Don't review it, just make sure the feature is there! Bad idea. Use another agent to do automatic review. (And a third agent writing tests.) Don't forget the architecting and orchestrating agent too!

Multiple agents with different frontier models for best results. Claude code/codex shops don’t know what they’re missing if they never let Gemini roast their designs, code and formal models.
Post reply on HN